© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19682
    Prev
    Next
    INDEX
    Explanations

    require statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uju
    -0.06
    etre
    -0.06
    æľĪåĪĬ
    -0.05
    upan
    -0.05
    ä¸įå®ļæľŁ
    -0.05
    nbsp
    -0.05
    åĬ¨åĬ¨
    -0.05
    itary
    -0.05
    è¡Ľ
    -0.05
    iya
    -0.05
    POSITIVE LOGITS
    æŃ£å¸¸å·¥ä½ľ
    0.06
    éģ
    0.06
     mains
    0.05
    omb
    0.05
     stren
    0.05
     normale
    0.05
    @student
    0.05
    almente
    0.05
    sem
    0.05
     compléter
    0.05
    Activations Density 0.188%

    No Known Activations